Noometry

Model comparison

GPT-5.4 vs Yi-34B

GPT-5.4 is the stronger model overall, scoring 59.4 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-5.4 scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 leads 65.3 to 7.5.
  • The biggest single-benchmark swing is GPQA Diamond: 93.3% for GPT-5.4 and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4Yi-34B
ProviderOpenAI01.AI
Noometry Index59.427.8
Released2026-03-052023-11-02
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2.50—
Output $ / M tokens$15—
Results tracked6823

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-5.4 leads

GPT-5.4: 52.6 (#33), Yi-34B: 32.3 (#274)

BenchmarkGPT-5.4Yi-34B
LMArena Coding14971112
SWE-bench Verified76.9%—
DeepSWE51.8%—
LMArena WebDev1465—
SciCode56.6%—
GSO31.4%—
WeirdML77.7%—
MirrorCode15.6%—
ALE-Bench1,607—
AlgoTune1.85—

Agentic & Tool Use Not comparable

GPT-5.4: 46.5 (#13), Yi-34B: —

BenchmarkGPT-5.4Yi-34B
Terminal-Bench81.8%—
APEX-Agents52.4%—
τ²-bench Banking39.4%—
DeepResearch Bench35.1%—
PostTrainBench19%—
GBAEval45.1%—
LMArena Search1197—
METR Time Horizons74.3%—
Vending-Bench 26,144—

Reasoning GPT-5.4 leads

GPT-5.4: 61.8 (#19), Yi-34B: 21.2 (#226)

BenchmarkGPT-5.4Yi-34B
LMArena Hard Prompts14851104
Epoch Capabilities Index156.81117.39
ARC-AGI-274%—
Kagi LLM Benchmark63.8%—
NYT Connections (extended)91.3%—
ARC-AGI-193.7%—
CritPt23.4%—
Chess Puzzles44%—
EnigmaEval16%—
Thematic Generalization80%—
EBR-Bench25.4%—
Mystery Game Puzzles37%—
DTBench94.4%—
LMCA52%—
BIG-Bench Hard—71.7%
ForecastBench59.5—

Math GPT-5.4 leads

GPT-5.4: 73.5 (#19), Yi-34B: 21.6 (#282)

BenchmarkGPT-5.4Yi-34B
LMArena Math14881114
FrontierMath (Tiers 1-3)78.6%—
FrontierMath Tier 449%—
MathArena Final-Answer Competitions83.1%—
OTIS Mock AIME 2024-202597.8%—
ProofBench56%—
MATH Level 5—5.1%
FrontierMath (Feb 2025 set)47.6%—
FrontierMath Tier 4 (v1)27.1%—
GSM8K—76%

Knowledge GPT-5.4 leads

GPT-5.4: 65.3 (#14), Yi-34B: 7.5 (#309)

BenchmarkGPT-5.4Yi-34B
GPQA Diamond93.3%14.7%
LMArena Expert15071061
Humanity's Last Exam36.2%—
SimpleQA Verified45.1%—
Vectara Hallucination Rate7%—
MMLU—76.3%

Multimodal Not comparable

GPT-5.4: 43.7 (#20), Yi-34B: —

BenchmarkGPT-5.4Yi-34B
LMArena Vision1303—
Blueprint-Bench 227.1%—
Furniture Assembly37.5%—
LMArena Document1471—

Multilingual GPT-5.4 leads

GPT-5.4: 56.2 (#23), Yi-34B: 29.7 (#264)

BenchmarkGPT-5.4Yi-34B
LMArena Non-English14651079
LMArena Chinese15191176
LMArena French14931081
LMArena German14721042
LMArena Japanese1485993
LMArena Korean1448959
LMArena Russian14801050
LMArena Spanish14541070

Instruction Following GPT-5.4 leads

GPT-5.4: 77.1 (#27), Yi-34B: 56.2 (#274)

BenchmarkGPT-5.4Yi-34B
LMArena Instruction Following14691091

Long Context GPT-5.4 leads

GPT-5.4: 50.3 (#8), Yi-34B: 33.2 (#264)

BenchmarkGPT-5.4Yi-34B
LMArena Longer Query14731094
CL-bench27.9%—
CL-bench Life21.7%—

Writing & Preference GPT-5.4 leads

GPT-5.4: 71.9 (#17), Yi-34B: 34.1 (#273)

BenchmarkGPT-5.4Yi-34B
LMArena Text14691129
LMArena Creative Writing14391108
LMArena Multi-Turn14821113
EQ-Bench Creative Writing1840—
EQ-Bench 41272—

Frequently asked questions

Is GPT-5.4 better than Yi-34B?

GPT-5.4 is the stronger model overall, scoring 59.4 to 27.8 on the Noometry Index.

Is GPT-5.4 or Yi-34B better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 32.3 in the Noometry coding category.

How many benchmarks do GPT-5.4 and Yi-34B share?

19 benchmarks have published results for both models. GPT-5.4 has 68 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper